# EnterpriseBench-CoreCraft leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/external-enterprise-bench-core-craft

EnterpriseBench: CoreCraft (Surge). Every model the catalog carries a published EnterpriseBench-CoreCraft value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Task success (%) |
| Tasks | Enterprise operations tasks in a simulated company |
| Difficulty | Multi-step enterprise tool use |
| Published by | [Introducing Inkling 2 Small](https://thinkingmachines.ai/news/inkling-2-small/) |

An enterprise-operations agent benchmark from Surge AI set in a simulated company (CoreCraft), where agents complete multi-step business tasks across internal tools and records.

## EnterpriseBench-CoreCraft ranking

1 model with a published EnterpriseBench-CoreCraft value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Task success (%) | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Inkling 2 Small](https://modelchoice.dev/models/inkling-2-small) | Thinking Machines Lab | 71.8 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
